arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2207.01792cs.LGcs.AI
收藏

基于特征的图对比学习自适应增强算法

Features Based Adaptive Augmentation for Graph Contrastive Learning

University of Science and Technology of China(中国科学技术大学)

Adnan Ali, Jinlong Li

摘要:

自监督学习旨在消除图表示学习中昂贵的注释,其中图对比学习(GCL)使用包含数据-数据对的自监督信号进行训练。这些数据-数据对是在原始图上使用随机函数增强而生成的。我们认为,某些特征可能比其他特征更关键,这取决于下游任务,并且均匀地应用随机函数会破坏有影响力的特征,导致准确性降低。为了解决这个问题,我们引入了一种基于特征的自适应增强(FebAA)方法,该方法可以识别和保留潜在的有影响力的特征,并破坏其余的特征。我们将FebAA实现为即插即用层,并将其与最先进的深度图对比学习(GRACE)和引导图潜在(BGRL)一起使用。我们成功地提高了八个图表示学习的基准数据集上的GRACE和BGRL的准确性。

英文摘要:

Self-Supervised learning aims to eliminate the need for expensive annotation in graph representation learning, where graph contrastive learning (GCL) is trained with the self-supervision signals containing data-data pairs. These data-data pairs are generated with augmentation employing stochastic functions on the original graph. We argue that some features can be more critical than others depending on the downstream task, and applying stochastic function uniformly, will vandalize the influential features, leading to diminished accuracy. To fix this issue, we introduce a Feature Based Adaptive Augmentation (FebAA) approach, which identifies and preserves potentially influential features and corrupts the remaining ones. We implement FebAA as plug and play layer and use it with state-of-the-art Deep Graph Contrastive Learning (GRACE) and Bootstrapped Graph Latents (BGRL). We successfully improved the accuracy of GRACE and BGRL on eight graph representation learning's benchmark datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑